Image analysis – Applications – Personnel identification
Reexamination Certificate
1999-11-09
2002-07-23
Mehta, Bhavesh (Department: 2611)
Image analysis
Applications
Personnel identification
C382S116000
Reexamination Certificate
active
06424727
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates in general to identification of physical characteristics of an animal and a human being. More particularly, the present invention relates to the identification of an animal and/or a person involved in an animal transaction using iris recognition.
BACKGROUND OF THE INVENTION
Animal identification has been in use for hundreds of years. The oldest form, acquaintance and recognition of animals by humans, is still in use. Newer techniques, such as ear tags, branding, and tattoos have been widely used but are susceptible to loss, illegibility, and mutilation concerns. DNA has been used, but this method is defeated by cloning. The newest methods are based on radio frequency identification (RFID) devices. These RFID devices typically include passive RF transponders that can be incorporated into collars, ear tags, injectible microcapsules, and rumen boluses. However, external RF devices are susceptible to theft, tampering, and mutilation while internal devices are intrusive and hard to maintain. Also, biological methods of identification have been proposed, such as antibody fingerprinting, which is one of the few techniques that can be used after the animal is slaughtered as well as before.
The requirements for animal identification vary depending on the application. Identification at or near birth is desirable for genetic and performance monitoring. For most other applications, such as animal health and food safety, it is sufficient to identify the animal at weaning or prior to its leaving the farm of origin.
In addition, fraud and deception in animal transactions and the theft of rare or valuable animals results in losses to animal owners and increased insurance claims. The costs of theses losses are passed on to consumers in the form of higher prices for animals and animal products. Automatic animal identification has been identified as a critical technology that can be used to meet industry needs for various animal transactions, including value based marketing, genetic improvement, breeding, animal tracking, health, disease control, and food safety. Additional, government requirements in some countries include population monitoring and certification to validate farm subsidies paid on a per-animal basis. For example, the requirement for accurate animal identification within the food industry is broad-based, and includes large food animals such as cattle, sheep, and swine. In addition, identification technology applicable to high-value animals, such as thoroughbred horses and racing dogs, is needed to prevent theft and fraud, and facilitate interstate and international movement of these animals in connection with equestrian events, competition, racing, and trading. Also, the authentication of animals used in breeding is needed to avoid fraud and deception and to ensure that the desired traits of an animal are passed on to the offspring.
In addition to identifying the animal, in certain animal transactions it is also desirable to positively identify persons involved in the animal identity and tracking chain, such as an owner, a shipper and transporting personnel, buyers and sellers, food processing personnel, veterinarians and animal care takers, etc. Currently, there is no reliable system for positively identifying an animal and at the same time also identifying the person in the identity and tracking chain who proposes to have an interest in or control over the animal. Matching the animal to its rightful owner or appointed guardian helps provide certainty in animal transactions and to ensure the safe and efficient transfer of animals between interested parties in order to minimize fraud, theft, uncertainty, and other risks normally present during most animal transactions.
Various technologies are used for uniquely identifying a person in accordance with an examination of particular attributes of either the person's interior or exterior eye. One of these technologies involves the visual examination of the particular attributes of the exterior of the iris of at least one of the person's eyes. The iris of an eye has random patterns of striations, ciliary processes, crypts, rings, furrows and other features which had been shown capable of generating highly unique biometric templates for identification purposes. In this regard, reference is made to U.S. Pat. No. 4,641,349, “Iris Recognition System”, issued to Flom et al., and U.S. Pat. No. 5,291,560, “Biometric Personal Identification System Based on Iris Analysis”, issued to Daugman. As made clear by these patents, the visible texture of a person's iris can be used to distinguish one person from another with great accuracy. Thus, iris recognition can be used for such purposes as controlling access to a secure facility or a bank automatic teller machine, for example. An iris recognition system involves the use of an imager to video image the iris of each person attempting access, and image processing means for comparing this iris video image with a reference iris image on file in a database.
Iris identification systems have been developed that are capable of collecting images of the iris of a person and processing them to produce biometric templates. These templates may be used to identify individual irises with extremely low error rates, on the order of 1 in 10
6
. The systems capture the iris images using stationary optical platforms that are often large, complex, and expensive. The systems are difficult to use with minimal cooperation of the subject being identified. As a result their usefulness in many applications is limited.
Although the art of iris recognition systems is well developed for humans, there remain some problems inherent in this technology, particularly the lack of a system and method for animal identification using iris recognition, as well as the lack of a system and method for using iris recognition for authorizing animal transactions with a high level of certainty in the validity and finality of the animal transaction. Therefore, a need exists for a recognition system and method that overcomes the drawbacks of the prior art.
SUMMARY OF THE INVENTION
The present invention is directed to a system and method for identification of animals based on features of the iris of the eye. An image of the eye is captured using an iris acquisition device that combines a camera, an optical system, an illumination source, and a viewing screen, preferably in one small, hand-held device. The illumination and imaging are capable of using visible and infrared light, preferably spanning a range of wavelengths from about 680 to about 800 nanometers. The viewing screen can be used to display the live image to an operator, who uses the displayed image to position and focus the device to obtain high quality images. Alternatively, automatic focusing features can be employed in capturing the images.
According to aspects of the invention, iris texture information is extracted from the image at multiple scales of analysis by a self-similar set of quadrature (2-D Gabor) bandpass filters defined in a dimensionless polar coordinate system. The sign of the projection of different parts of the iris onto these multi-scale filters determines each bit in a biometric code (e.g., an abstract 256-byte iris code). The resulting biometric code has fixed length and format, facilitating comparison of multiple codes at high speed using simple digital exclusive-or (XOR) logic. A similarity metric, the Hamming distance, is computed from any two biometric codes. The value of this metric positively confirms or disconfirms the identity of an individual animal by comparing its biometric code with a previously-obtained biometric template, collected under conditions which permit independent verification of identity, and stored in a database along with identification information.
The present invention is directed to a system and method of animal identification. The system can authenticate the claimed identity of an animal and identify an unknown animal by comparing a captured iris image on an animal t
Cambier James L.
Musgrave Clyde
Iridian Technologies, Inc.
Mehta Bhavesh
Woodcock & Washburn LLP
LandOfFree
System and method of animal identification and animal... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method of animal identification and animal..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method of animal identification and animal... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2838413